1 / 1

Achievements

(Fuzzy Logic Inferencing Pong). Objectives. Methods. Results. Create Simulation Observe Human Collaboration: Tennis Matches Create Fuzzy Inference System Models Human-Like Behavior Beta Testing Compile Results. Create a doubles PONG game with: Advanced ball control

gay
Download Presentation

Achievements

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. (Fuzzy Logic Inferencing Pong) Objectives Methods Results • Create Simulation • Observe Human Collaboration: Tennis Matches • Create Fuzzy Inference System • Models Human-Like Behavior • Beta Testing • Compile Results Create a doubles PONG game with: • Advanced ball control • Rotation of paddles • 2-on-2 gameplay • Fuzzy Logic based opponents University of Cincinnati, Department of Aerospace Engineering Added degree of freedom to PONG New bounce capabilities (angel of incidence) Improved Boundary Conditions Rotate/Translate Simultaneously Humans vs. Robots Capable Robots vs. Robots Capable FUZZyTimeE-critical Spatio-Temporal Pong (FUZZ-TEST Pong) Achievements Brandon Cook Faculty Mentor: Kelly Cohen • Strategy • Larger paddle rotations: more offensive • Fuzzy Reasoning • Example of how Fuzzy Paddles assign discrete outputs Introduction Figure 5: Breakdown of Fuzzy Paddle (Offensive vs. Defensive) • Fuzzy Logic • Allows classification of variables for more human-like reasoning • Common terms: • Inputs • Rules • Outputs • Membership Function • Fuzzy Inference System (FIS) • Back up partner: more defensive Figure 7: Added Rotational Degree of Freedom Conclusion • Fuzzy logic is an effective tool for: • Emulating human-like reasoning • Collaborative linguistic reasoning between autonomous robots • Adapting to situations where linear model controllers are not feasible Figure 3: Fuzzy Logic Reasoning Figure 6: Fuzzy Team Defensive Strategy (Red Team) • Fuzzy Inference System (FIS) • Example of strategy FIS • PONG • Classic arcade game created by Atari • Gameplay Objective: Score by hitting the ball past opponent • First team to 21 points wins • Creates spatio-temporal environment Figure 1: The light spectrum is fuzzy, as is nature. Future Work Beta Testing Adding varying degrees of difficulty selections • Easy, Medium, Hard Add trickery components to Intelligent Team Additional inputs and modified outputs to take opponents current rotation in to account Implement collaborative robotics into real world, 3-dimensional, simulation (e.g. disaster relief situations) Table 1: Doubles Robot Team vs. Robot Team Results • Simulation proved Fuzzy teams are evenly matched • Each volley lasted nearly 5 minutes • Logic proved effective at : • Intercepting ball trajectory • Hitting ball towards open court positions Figure 2: Doubles Pong Setup Figure 5. Real-World Collaborative Robots (i.e. Naos) Table 2: Doubles Human Team vs. Robot Team Results Figure 4: Fuzzy Inference System (FIS) File References Acknowledgements • Match #1 (first to 21 points) • Robots defeated Humans 21 to 2 • Only scores on Robots due to small gameplay glitches (e.g. ball traveling through paddle) • Match #2 (first to 21 points) • Robots defeated Humans 21 to 0 • Proved effectiveness of Fuzzy Logic Paddles • Sponsored by: The National Science Foundation • Grand ID No.: DUE-0756921 • Academic Year – Research Experience for Undergraudates (AY-REU) Program • Sophia Mitchell • Original FLIP Simulation Creator (only translation) • Depending on Inputs: • Unoccupied regions of the court (Open) • Game Strategy: offensive/defensive (Game) • Current fuzzy paddle location • Assign discrete output strategy: Where to hit the ball (Strategy) • Kosko, Bart. Fuzzy Thinking: The New Science of Fuzzy Logic. New York: Hyperion, 1993. Print. • Mendel, Jerry M., and Dongrui Wu. "Interval Type-2 Fuzzy Sets." Perceptual Computing: Aiding People in Making Subjective Judgments. Piscataway, NJ: IEEE, 2010. 35-64. Print. • 2010 Australian Open – Men’s Doubles Final Bob & Mike Bryan vs. Nestor & Zimonjic [video]. Retrieved June, 2011, from http://www. youtube. com/watch?v=0C-pEt8d9ts • Barker, S. , Sabo, C. , and Cohen, K. , "Intelligent Algorithms for MAZE Exploration and Exploitation", AIAA Infotech@Aerospace Conference, St. Louis, MO, March 29-31, 2011, AIAA Paper 2011-1510. • D. Buckingham, Dave’s MATLAB Pong, University of Vermont, Matlab Central, 2011 • Federer & Mirka vs. Hewitt & Molik – part 3 [video]. Retrieved June, 2011, from http://www. youtube. com/watch?v=b0BAh_pRRTo • Sng H. L. , Sen Gupta and C. H. Messom, Strategy for Collaboration in Robot Soccer, IEEE International Workshop on Electronic Design, Test and Applications (DELTA), 2002 • B. Innocenti, B. Lopez and J. Salvi, A Multi-Agent Architecture with Cooperative Fuzzy Control for a Mobile Robot, Robotics and Autonomous Systems, vol. 55, pp. 881-891, 2007 • D. Matko, G. Klancar and M. Lepetic, A Tool for the Analysis of Robot Soccer Game, International Journal of Control, Automation and Systems, vol. 1, pp. 222 – 228, 2003

More Related